Start with text. Add images, video clips, or audio when your scene needs more direction. Then use @-reference tags to show the model what each asset should do. The result is a 5–15 second video built for connected, cinematic storytelling.
Seedance 2.0 is for creators, filmmakers, marketers, and e-commerce teams who need more than a single silent clip. It is a strong fit when you want to use reference assets and direct the story, sound, or camera role together.
It is less suitable when you only need a static image. Use it when you want to turn visual inputs into a short video sequence.
The practical difference is simple: you direct a scene instead of generating a generic clip. Give each input a clear role. Then review the result as a coherent piece of video and audio.
Use text, images, video, audio, or a combination of them. One generation can use up to 12 reference files: up to nine images, three video clips, and three audio clips. Video and audio clips can be up to 15 seconds each.
Use @-reference tags to make the prompt easier to follow. You can indicate a first frame, a camera reference, or background music, then describe the action and tone of the scene.
Seedance 2.0 creates 5–15 second, multi-shot video at up to 2K resolution and 24 fps. Choose from 21:9, 16:9, 4:3, 1:1, 3:4, or 9:16 to match the delivery format.
Seedance 2.0 access lets you combine text, image, video, and audio inputs. This lets you use a written direction with reference material instead of relying on text alone.
Seedance 2.0 generates video and audio in the same pass. The output can include dialogue with lip-sync in 8+ languages, ambient sound effects, and background music.
Direct character movement, environmental sound, and camera angle across a sequence. The model is designed to keep the scene and story moving together across cuts.
Build short-form video for TikTok, YouTube Shorts, and Instagram Reels from a prompt and supporting assets. Choose an aspect ratio that fits the channel before you generate.
Use the model to pre-visualize scenes, explore B-roll directions, or prototype a multi-camera sequence. It gives a team a concrete visual conversation before a shoot.
Turn product photos into dynamic lifestyle video with sound. For a practical starting point, see e-commerce workflows or browse all models when you want to compare creative options.
Get access to Seedance 2.0 and all premium AI models with one membership.
For hobbyists and explorers
For creators and pro users
For power users and teams
For teams and studios
Everything you need to know about Seedance 2.0.
You can use the Seedance 2.0 model directly on YouArt. Choose the model, add your prompt and optional reference assets, then start a generation.
Seedance 2.0 access gives you a more direct way to turn a written idea and reference assets into a short video with synchronized sound. Bring the key inputs. Define their roles. Then start the sequence.
